Получить продукт по id. Если не найден — error.
AI agents call get_product to retrieve information from Product Agent MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple lookup operation in the product database. It retrieves existing data without modifying, deleting, or executing code. The only outcome is returning product information or an error message. This is a classic Read operation with low severity risk, as misuse would only expose existing data rather than causing destructive or financial harm.
From the tool's definition Tool name is 'get_product' and description states 'Получить продукт по id' (Get product by id). This is a retrieval operation with no side effects—it queries a product database and returns data or an error if not found.
Attacks that exploit this kind of access
Получить продукт по id. Если не найден — error. It is categorised as a Read tool in the Product Agent MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Product Agent MCP Server MCP server in PolicyLayer and add a rule for get_product: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Product Agent MCP Server. Nothing to install.
get_product is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_product rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_product. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_product is provided by the Product Agent MCP Server MCP server (zhangeldi123/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →